cosine_similarity() — langchain Function Reference

Architecture documentation for the cosine_similarity() function in vectorstores.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 1

Entity Profile

LangChainCore→ MessageInterface→ cosine_similarity() — langchain Function Reference

Dependency Diagram

graph TD
  edb939a7_b329_2e7a_29d5_0bf2e63f4460["cosine_similarity()"]
  22063c60_48df_f64e_d9d8_9b17dc13659a["vectorstores.py"]
  edb939a7_b329_2e7a_29d5_0bf2e63f4460 -->|defined in| 22063c60_48df_f64e_d9d8_9b17dc13659a
  4b1eec22_ecb8_c99c_8a5f_bbe2249bd26f["maximal_marginal_relevance()"]
  4b1eec22_ecb8_c99c_8a5f_bbe2249bd26f -->|calls| edb939a7_b329_2e7a_29d5_0bf2e63f4460
  style edb939a7_b329_2e7a_29d5_0bf2e63f4460 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/chroma/langchain_chroma/vectorstores.py lines 79–106

def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:  # type: ignore[valid-type]
    """Row-wise cosine similarity between two equal-width matrices.

    Raises:
        ValueError: If the number of columns in X and Y are not the same.
    """
    if len(X) == 0 or len(Y) == 0:
        return np.array([])

    X = np.array(X)
    Y = np.array(Y)
    if X.shape[1] != Y.shape[1]:
        msg = (
            "Number of columns in X and Y must be the same. X has shape"
            f"{X.shape} "
            f"and Y has shape {Y.shape}."
        )
        raise ValueError(
            msg,
        )

    X_norm = np.linalg.norm(X, axis=1)
    Y_norm = np.linalg.norm(Y, axis=1)
    # Ignore divide by zero errors run time warnings as those are handled below.
    with np.errstate(divide="ignore", invalid="ignore"):
        similarity = np.dot(X, Y.T) / np.outer(X_norm, Y_norm)
    similarity[np.isnan(similarity) | np.isinf(similarity)] = 0.0
    return similarity